
NVIDIA Unveils Vera Rubin AI Platform at CES 2026
California, United States
5 min read
Updated By: History Editorial Network (HEN)
Published:
NVIDIA introduced its next generation Vera Rubin AI platform during CES 2026 in Las Vegas, presenting a new rack scale computing system designed for large artificial intelligence workloads and data center operations. The announcement was made by NVIDIA founder and CEO Jensen Huang during the company’s CES keynote on 05/01/2026 at the Fontainebleau Las Vegas venue. The Rubin platform succeeds NVIDIA’s Blackwell architecture and combines multiple hardware technologies into a single AI infrastructure system.
The Vera Rubin platform includes six integrated components: the Vera CPU, Rubin GPU, NVLink 6 switch, ConnectX 9 SuperNIC, BlueField 4 DPU, and Spectrum 6 Ethernet switch. NVIDIA described the design as an “AI supercomputer” intended for training and inference workloads across cloud computing, robotics, autonomous vehicles, and enterprise AI systems. According to NVIDIA, each Rubin GPU delivers up to 50 petaflops of inference performance using the NVFP4 format, while the Vera Rubin NVL72 rack system can provide up to 3.6 exaflops of inference performance.
During the CES presentation, Jensen Huang said demand for AI computing capacity was “going through the roof” as companies increasingly build large scale AI factories and autonomous systems. NVIDIA also stated that the Rubin platform could reduce the number of GPUs required for some mixture of experts AI models by up to 75 percent compared with Blackwell generation systems, while lowering token generation costs. The company confirmed that major cloud providers including AWS, Google Cloud, Microsoft Azure, and Oracle Cloud Infrastructure were expected to deploy Vera Rubin based systems beginning in 2026.
The platform was named after astronomer Vera Rubin, known for her work on galaxy rotation and evidence supporting dark matter research. Industry analysts and technology publications noted that NVIDIA’s CES 2026 presentation focused heavily on scaling AI infrastructure beyond traditional graphics processing into broader industrial and enterprise computing systems. The launch also included announcements related to robotics, autonomous driving technology, and AI networking products connected to the Rubin ecosystem.
#NVIDIA #CES2026 #VeraRubin #ArtificialIntelligence #AIInfrastructure #JensenHuang #DataCenters
Primary Reference
Nvidia
